SciCapenter: Supporting Caption Composition for Scientific Figures with Machine-Generated Captions and Ratings
This addresses the challenge of writing effective captions for scientific figures, which is crucial for readers' understanding, though it is incremental as it integrates existing AI technologies into a new interactive tool.
The paper tackles the problem of aiding caption composition for scientific figures by introducing SciCapenter, an interactive system that generates multiple captions with quality ratings, resulting in significantly lower cognitive load for users, as indicated by a user study with Ph.D. students.
Crafting effective captions for figures is important. Readers heavily depend on these captions to grasp the figure's message. However, despite a well-developed set of AI technologies for figures and captions, these have rarely been tested for usefulness in aiding caption writing. This paper introduces SciCapenter, an interactive system that puts together cutting-edge AI technologies for scientific figure captions to aid caption composition. SciCapenter generates a variety of captions for each figure in a scholarly article, providing scores and a comprehensive checklist to assess caption quality across multiple critical aspects, such as helpfulness, OCR mention, key takeaways, and visual properties reference. Users can directly edit captions in SciCapenter, resubmit for revised evaluations, and iteratively refine them. A user study with Ph.D. students indicates that SciCapenter significantly lowers the cognitive load of caption writing. Participants' feedback further offers valuable design insights for future systems aiming to enhance caption writing.